agent-browser

agent-browser is a skill for Claude Code, Codex from mifunedev/openharness. It costs 68 tokens per session (1,806 once invoked), scanned B, original, Apache-2.0.

A skill for opening web pages in agent-browser, a headless browser that visits sites without displaying a normal browser window. It checks that the browser and Chromium can launch before navigating.

In plain words
What is it for?
Use it to open URLs, choose desktop or mobile viewport sizes, keep sessions isolated, take screenshots, or test a website.
Why use it?
It catches browser setup problems early and provides a diagnostic trace when a page cannot be opened.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mifunedev/openharness/agent-browser
Any agent
npx skills add mifunedev/openharness --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/mifunedev/openharness

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/mifunedev/openharness/agent-browser.svg)](https://agentmods.dev/skills/mifunedev/openharness/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/mifunedev/openharness/agent-browser"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/agent-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00068 $0.01806
Opus 5 $0.00034 $0.00903
Sonnet 5 $0.00014 $0.00361
Haiku 4.5 $0.00007 $0.00181

Measured today against content hash dc465db5ca93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agent-browser scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Do not reach for `sudo npm install -g`.** It lands under

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

IP=$(curl -sf "https://cloudflare-dns.com/dns-query?name=${HOSTNAME}&type=A" \
.oh/skills/agent-browser/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Browser

Open a URL in the headless browser. Runs a health check first — if the browser is broken, errors out with a full diagnostic trace so the user can fix it.

Instructions

Step 1 — Parse arguments

Arguments received: $ARGUMENTS

  • URL: $0 (required)
  • VIEWPORT: value after --viewport flag if present. Default: desktop
  • SESSION: value after --session flag if present (optional, for session isolation)

If URL is missing, ask the user to provide it.

Viewport defaults

Name Width Height
desktop 1280 720
mobile 414 896

Default is desktop if --viewport is not specified.

Step 2 — Preflight health check

Run each check sequentially. If any check fails, stop immediately and report the full diagnostic trace to the user.

2a. Check agent-browser is installed
command -v agent-browser && agent-browser --version 2>&1 || echo "FAIL: agent-browser not found in PATH"

If not found, install it through the CLI — the catalog entry pins the version, fixes the binary's mode, and runs agent-browser install --with-deps for you:

oh tool install agent-browser --yes

--yes is required whenever stdin is not a TTY: the entry declares a ~1 GB download, and the confirmation gate refuses rather than prompting.

Verify:

agent-browser --version     # → agent-browser 0.8.5
agent-browser open about:blank && agent-browser close

Notes:

  • 0.8.5 — later majors have breaking CLI changes; the rest of this skill targets 0.8.5's flags. The catalog owns the pin.
  • Do not reach for sudo npm install -g. It lands under /usr/lib/node_modules, which no running sandbox can upgrade in place. Use oh tool install agent-browser: the catalog installs into $PNPM_HOME under the sandbox user's own home.
  • If agent-browser install --with-deps ever ends with sh: 1: playwright: not found, the playwright CLI is missing: npx playwright install chromium after pnpm add -g playwright@latest.

Read the full file on GitHub · 202 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · -4 lines dc465db5ca93
  2. 4d ago First seen · 206 lines · 68 tokens per session scan B 5d5367320c47

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 1,806 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

textual-screenshot

Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.

langchain-ai/deepagents · 67 tokens

data-visualization

Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.

langchain-ai/deepagents · 40 tokens

cuml-machine-learning

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

langchain-ai/deepagents · 43 tokens

blog-post

Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.

langchain-ai/deepagents · 58 tokens

social-media

Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.

langchain-ai/deepagents · 58 tokens

remember

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…

langchain-ai/deepagents · 71 tokens